The Journal of China Universities of Posts and Telecommunications ›› 2023, Vol. 30 ›› Issue (3): 1-13.doi: 10.19682/j.cnki.1005-8885.2023.1002

• Artificial intelligence •     Next Articles

RB-SLAM: visual SLAM based on rotated BEBLID feature point description

Fan Xinyue, Wu Kai, Chen Shuai   

  1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2022-05-25 Revised:2023-03-20 Online:2023-06-30 Published:2023-06-30
  • Contact: Wu Kai E-mail:s200131326@stu.cqupt.edu.cn

Abstract:

The extraction and description of image features are very important for visual simultaneous localization and mapping (V-SLAM). A rotated boosted efficient binary local image descriptor ( BEBLID) SLAM ( RB-SLAM) algorithm based on improved oriented fast and rotated brief (ORB) feature description is proposed in this paper, which can solve the problems of low localization accuracy and time efficiency of the current ORB-SLAM3 algorithm. Firstly, it uses the BEBLID to replace the feature point description algorithm of the original ORB to enhance the expressiveness and description efficiency of the image. Secondly, it adds rotational invariance to the BEBLID using the orientation information of the feature points. It also selects the rotationally stable bits in the BEBLID to further enhance the rotational invariance of the BEBLID. Finally, it retrains the binary visual dictionary based on the BEBLID to reduce the cumulative error of V-SLAM and improve the loading speed of the visual dictionary. Experiments show that the dictionary loading efficiency is improved by more than 10 times. The RB-SLAM algorithm improves the trajectory accuracy by 24.75% on the TUM dataset and 26.25% on the EuRoC dataset compared to the ORB-SLAM3 algorithm.

Key words: visual simultaneous localization and mapping (V-SLAM), oriented fast and rotated brief (ORB), feature extraction, boosted efficient binary local image descriptor (BEBLID), rotational invariance

CLC Number: